#آموزش
نوت بوک آموزشی تنسرفلوی 2
https://github.com/ageron/tf2_course
#tensorflow
----------
@machinelearning_tuts
نوت بوک آموزشی تنسرفلوی 2
https://github.com/ageron/tf2_course
#tensorflow
----------
@machinelearning_tuts
GitHub
GitHub - ageron/tf2_course: Notebooks for my "Deep Learning with TensorFlow 2 and Keras" course
Notebooks for my "Deep Learning with TensorFlow 2 and Keras" course - ageron/tf2_course
Fortifying the future of cryptography
Vinod Vaikuntanathan aims to improve encryption in a world with growing applications and evolving adversaries.
@machinelearning_tuts
----------
Link : http://news.mit.edu//2019/faculty-vinod-vaikuntanathan-0116
Vinod Vaikuntanathan aims to improve encryption in a world with growing applications and evolving adversaries.
January 16, 2019
@machinelearning_tuts
----------
Link : http://news.mit.edu//2019/faculty-vinod-vaikuntanathan-0116
A Unified Framework of Deep Neural Networks by Capsules
--Abstract
With the growth of deep learning, how to describe deep neural networksunifiedly is becoming an important issue. We first formalize neural networksmathematically with their directed graph representations, and prove ageneration theorem about the induced networks of connected directed acyclicgraphs. Then, we set up a unified framework for deep learning with capsulenetworks. This capsule framework could simplify the description of existingdeep neural networks, and provide a theoretical basis of graphic designing andprogramming techniques for deep learning models, thus would be of greatsignificance to the advancement of deep learning.
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1805.03551v2
--Abstract
With the growth of deep learning, how to describe deep neural networksunifiedly is becoming an important issue. We first formalize neural networksmathematically with their directed graph representations, and prove ageneration theorem about the induced networks of connected directed acyclicgraphs. Then, we set up a unified framework for deep learning with capsulenetworks. This capsule framework could simplify the description of existingdeep neural networks, and provide a theoretical basis of graphic designing andprogramming techniques for deep learning models, thus would be of greatsignificance to the advancement of deep learning.
2018-05-09T14:23:17Z
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1805.03551v2
arXiv.org
A Unified Framework of Deep Neural Networks by Capsules
With the growth of deep learning, how to describe deep neural networks unifiedly is becoming an important issue. We first formalize neural networks mathematically with their directed graph...
Deep Learning for Sentiment Analysis : A Survey
--Abstract
Deep learning has emerged as a powerful machine learning technique thatlearns multiple layers of representations or features of the data and producesstate-of-the-art prediction results. Along with the success of deep learning inmany other application domains, deep learning is also popularly used insentiment analysis in recent years. This paper first gives an overview of deeplearning and then provides a comprehensive survey of its current applicationsin sentiment analysis.
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1801.07883v2
--Abstract
Deep learning has emerged as a powerful machine learning technique thatlearns multiple layers of representations or features of the data and producesstate-of-the-art prediction results. Along with the success of deep learning inmany other application domains, deep learning is also popularly used insentiment analysis in recent years. This paper first gives an overview of deeplearning and then provides a comprehensive survey of its current applicationsin sentiment analysis.
2018-01-24T07:32:29Z
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1801.07883v2
arXiv.org
Deep Learning for Sentiment Analysis : A Survey
Deep learning has emerged as a powerful machine learning technique that
learns multiple layers of representations or features of the data and produces
state-of-the-art prediction results. Along...
learns multiple layers of representations or features of the data and produces
state-of-the-art prediction results. Along...
Integrating Learning and Reasoning with Deep Logic Models
--Abstract
Deep learning is very effective at jointly learning feature representationsand classification models, especially when dealing with high dimensional inputpatterns. Probabilistic logic reasoning, on the other hand, is capable to takeconsistent and robust decisions in complex environments. The integration ofdeep learning and logic reasoning is still an open-research problem and it isconsidered to be the key for the development of real intelligent agents. Thispaper presents Deep Logic Models, which are deep graphical models integratingdeep learning and logic reasoning both for learning and inference. Deep LogicModels create an end-to-end differentiable architecture, where deep learnersare embedded into a network implementing a continuous relaxation of the logicknowledge. The learning process allows to jointly learn the weights of the deeplearners and the meta-parameters controlling the high-level reasoning. Theexperimental results show that the proposed methodology overtakes thelimitations of the other approaches that have been proposed to bridge deeplearning and reasoning.
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1901.04195v1
--Abstract
Deep learning is very effective at jointly learning feature representationsand classification models, especially when dealing with high dimensional inputpatterns. Probabilistic logic reasoning, on the other hand, is capable to takeconsistent and robust decisions in complex environments. The integration ofdeep learning and logic reasoning is still an open-research problem and it isconsidered to be the key for the development of real intelligent agents. Thispaper presents Deep Logic Models, which are deep graphical models integratingdeep learning and logic reasoning both for learning and inference. Deep LogicModels create an end-to-end differentiable architecture, where deep learnersare embedded into a network implementing a continuous relaxation of the logicknowledge. The learning process allows to jointly learn the weights of the deeplearners and the meta-parameters controlling the high-level reasoning. Theexperimental results show that the proposed methodology overtakes thelimitations of the other approaches that have been proposed to bridge deeplearning and reasoning.
2019-01-14T09:06:28Z
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1901.04195v1
arXiv.org
Integrating Learning and Reasoning with Deep Logic Models
Deep learning is very effective at jointly learning feature representations
and classification models, especially when dealing with high dimensional input
patterns. Probabilistic logic reasoning,...
and classification models, especially when dealing with high dimensional input
patterns. Probabilistic logic reasoning,...
Why walk when you can flop?
In one example, a simulated robot was supposed to evolve to travel as quickly as possible. But rather than evolve legs, it simply assembled itself into a tall tower, then fell over. Some of these robots even learned to turn their falling motion into a somersault, adding extra distance.
Blog by Janelle Shane: https://lnkd.in/dQnCVa9
Original paper: https://lnkd.in/dt63hJR
#algorithm #artificialintelligence #machinelearning #reinforcementlearning #technology
----------
@machinelearning_tuts
In one example, a simulated robot was supposed to evolve to travel as quickly as possible. But rather than evolve legs, it simply assembled itself into a tall tower, then fell over. Some of these robots even learned to turn their falling motion into a somersault, adding extra distance.
Blog by Janelle Shane: https://lnkd.in/dQnCVa9
Original paper: https://lnkd.in/dt63hJR
#algorithm #artificialintelligence #machinelearning #reinforcementlearning #technology
----------
@machinelearning_tuts
NEW YOUTUBE VIDEO: This elevation system protects your home from storms.
Watch ►►► https://youtu.be/OpO3mE50Tc0
----------
@machinelearning_tuts
Watch ►►► https://youtu.be/OpO3mE50Tc0
----------
@machinelearning_tuts
YouTube
This Elevation System Protects Your Home From Storms And Floods
This is a fool-proof system that prepares your homes when storms and floods strike. Link To Source: http://pattersonshoring.com/ ►►► Subscribe now: https://w...
DeepFlash is a nice application of auto-encoders where they trained a neural network to turn a flash selfie into a studio portrait. It's an interesting paper with a real need, I seriously mean it! They've also tested their results against other approaches like pix2pix, style transfer etc.. Somehow from the first glance I had the feeling that pix2pix performed better than their suggested approach but their evaluation metrics (SSIM and PSNR) proved me wrong.
#deeplearning #machinelearning
Paper link: https://lnkd.in/eHM5rRx
----------
@machinelearning_tuts
#deeplearning #machinelearning
Paper link: https://lnkd.in/eHM5rRx
----------
@machinelearning_tuts
Machine Learning Guide: 20 Free ODSC Resources to Learn Machine Learning: https://lnkd.in/ejqejpA
#BigData #DataScience #DataScientists #AI #DeepLearning
----------
@machinelearning_tuts
#BigData #DataScience #DataScientists #AI #DeepLearning
----------
@machinelearning_tuts
How do you go from self-play to the real world? : Transfer learning
NeurIPS 2017 Meta Learning Symposium: https://lnkd.in/e7MdpPc
A new research problem has therefore emerged: How can the complexity, i.e. the design, components, and hyperparameters, be configured automatically so that these systems perform as well as possible? This is the problem of metalearning. Several approaches have emerged, including those based on Bayesian optimization, gradient descent, reinforcement learning, and evolutionary computation.
#artificialintelligence #deeplearning #metalearning #reinforcementlearning
----------
@machinelearning_tuts
NeurIPS 2017 Meta Learning Symposium: https://lnkd.in/e7MdpPc
A new research problem has therefore emerged: How can the complexity, i.e. the design, components, and hyperparameters, be configured automatically so that these systems perform as well as possible? This is the problem of metalearning. Several approaches have emerged, including those based on Bayesian optimization, gradient descent, reinforcement learning, and evolutionary computation.
#artificialintelligence #deeplearning #metalearning #reinforcementlearning
----------
@machinelearning_tuts
Delira was developed as a deep learning framework for medical images such as CT or MRI. Currently, it works on arbitrary data (based on NumPy).
Based on PyTorch, batchgenerators and trixi it provides a framework for
Dataset loading
Dataset sampling
Augmentation (multi-threaded) including 3D images with any number of channels
A generic trainer class that implements the training process
Already implemented models used in medical image processing and exemplaric implementations of most used models in general (like Resnet)
Web-based monitoring using Visdom
Model save and load functions
Delira supports classification and regression problems as well as generative adversarial networks and segmentation tasks.
#منابع #یادگیری_عمیق
Getting Started: https://lnkd.in/efeU8vv
----------
@machinelearning_tuts
Based on PyTorch, batchgenerators and trixi it provides a framework for
Dataset loading
Dataset sampling
Augmentation (multi-threaded) including 3D images with any number of channels
A generic trainer class that implements the training process
Already implemented models used in medical image processing and exemplaric implementations of most used models in general (like Resnet)
Web-based monitoring using Visdom
Model save and load functions
Delira supports classification and regression problems as well as generative adversarial networks and segmentation tasks.
#منابع #یادگیری_عمیق
Getting Started: https://lnkd.in/efeU8vv
----------
@machinelearning_tuts
When deep learning meets security
--Abstract
Deep learning is an emerging research field that has proven its effectivenesstowards deploying more efficient intelligent systems. Security, on the otherhand, is one of the most essential issues in modern communication systems.Recently many papers have shown that using deep learning models can achievepromising results when applied to the security domain. In this work, we providean overview for the recent studies that apply deep learning techniques to thefield of security.
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1807.04739v1
--Abstract
Deep learning is an emerging research field that has proven its effectivenesstowards deploying more efficient intelligent systems. Security, on the otherhand, is one of the most essential issues in modern communication systems.Recently many papers have shown that using deep learning models can achievepromising results when applied to the security domain. In this work, we providean overview for the recent studies that apply deep learning techniques to thefield of security.
2018-07-12T17:44:42Z
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1807.04739v1
arXiv.org
When deep learning meets security
Deep learning is an emerging research field that has proven its effectiveness
towards deploying more efficient intelligent systems. Security, on the other
hand, is one of the most essential issues...
towards deploying more efficient intelligent systems. Security, on the other
hand, is one of the most essential issues...
Are Efficient Deep Representations Learnable?
--Abstract
Many theories of deep learning have shown that a deep network can requiredramatically fewer resources to represent a given function compared to ashallow network. But a question remains: can these efficient representations belearned using current deep learning techniques? In this work, we test whetherstandard deep learning methods can in fact find the efficient representationsposited by several theories of deep representation. Specifically, we train deepneural networks to learn two simple functions with known efficient solutions:the parity function and the fast Fourier transform. We find that usinggradient-based optimization, a deep network does not learn the parity function,unless initialized very close to a hand-coded exact solution. We also find thata deep linear neural network does not learn the fast Fourier transform, even inthe best-case scenario of infinite training data, unless the weights areinitialized very close to the exact hand-coded solution. Our results suggestthat not every element of the class of compositional functions can be learnedefficiently by a deep network, and further restrictions are necessary tounderstand what functions are both efficiently representable and learnable.
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1807.06399v1
--Abstract
Many theories of deep learning have shown that a deep network can requiredramatically fewer resources to represent a given function compared to ashallow network. But a question remains: can these efficient representations belearned using current deep learning techniques? In this work, we test whetherstandard deep learning methods can in fact find the efficient representationsposited by several theories of deep representation. Specifically, we train deepneural networks to learn two simple functions with known efficient solutions:the parity function and the fast Fourier transform. We find that usinggradient-based optimization, a deep network does not learn the parity function,unless initialized very close to a hand-coded exact solution. We also find thata deep linear neural network does not learn the fast Fourier transform, even inthe best-case scenario of infinite training data, unless the weights areinitialized very close to the exact hand-coded solution. Our results suggestthat not every element of the class of compositional functions can be learnedefficiently by a deep network, and further restrictions are necessary tounderstand what functions are both efficiently representable and learnable.
2018-07-17T13:08:21Z
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1807.06399v1
arXiv.org
Are Efficient Deep Representations Learnable?
Many theories of deep learning have shown that a deep network can require
dramatically fewer resources to represent a given function compared to a
shallow network. But a question remains: can...
dramatically fewer resources to represent a given function compared to a
shallow network. But a question remains: can...
Deep Learning for Genomics: A Concise Overview
--Abstract
Advancements in genomic research such as high-throughput sequencingtechniques have driven modern genomic studies into "big data" disciplines. Thisdata explosion is constantly challenging conventional methods used in genomics.In parallel with the urgent demand for robust algorithms, deep learning hassucceeded in a variety of fields such as vision, speech, and text processing.Yet genomics entails unique challenges to deep learning since we are expectingfrom deep learning a superhuman intelligence that explores beyond our knowledgeto interpret the genome. A powerful deep learning model should rely oninsightful utilization of task-specific knowledge. In this paper, we brieflydiscuss the strengths of different deep learning models from a genomicperspective so as to fit each particular task with a proper deep architecture,and remark on practical considerations of developing modern deep learningarchitectures for genomics. We also provide a concise review of deep learningapplications in various aspects of genomic research, as well as pointing outpotential opportunities and obstacles for future genomics applications.
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1802.00810v2
--Abstract
Advancements in genomic research such as high-throughput sequencingtechniques have driven modern genomic studies into "big data" disciplines. Thisdata explosion is constantly challenging conventional methods used in genomics.In parallel with the urgent demand for robust algorithms, deep learning hassucceeded in a variety of fields such as vision, speech, and text processing.Yet genomics entails unique challenges to deep learning since we are expectingfrom deep learning a superhuman intelligence that explores beyond our knowledgeto interpret the genome. A powerful deep learning model should rely oninsightful utilization of task-specific knowledge. In this paper, we brieflydiscuss the strengths of different deep learning models from a genomicperspective so as to fit each particular task with a proper deep architecture,and remark on practical considerations of developing modern deep learningarchitectures for genomics. We also provide a concise review of deep learningapplications in various aspects of genomic research, as well as pointing outpotential opportunities and obstacles for future genomics applications.
2018-02-02T12:50:25Z
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1802.00810v2
arXiv.org
Deep Learning for Genomics: A Concise Overview
Advancements in genomic research such as high-throughput sequencing
techniques have driven modern genomic studies into "big data" disciplines. This
data explosion is constantly challenging...
techniques have driven modern genomic studies into "big data" disciplines. This
data explosion is constantly challenging...
Deep Learning: A Critical Appraisal
--Abstract
Although deep learning has historical roots going back decades, neither theterm "deep learning" nor the approach was popular just over five years ago,when the field was reignited by papers such as Krizhevsky, Sutskever andHinton's now classic (2012) deep network model of Imagenet. What has the fielddiscovered in the five subsequent years? Against a background of considerableprogress in areas such as speech recognition, image recognition, and gameplaying, and considerable enthusiasm in the popular press, I present tenconcerns for deep learning, and suggest that deep learning must be supplementedby other techniques if we are to reach artificial general intelligence.
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1801.00631v1
--Abstract
Although deep learning has historical roots going back decades, neither theterm "deep learning" nor the approach was popular just over five years ago,when the field was reignited by papers such as Krizhevsky, Sutskever andHinton's now classic (2012) deep network model of Imagenet. What has the fielddiscovered in the five subsequent years? Against a background of considerableprogress in areas such as speech recognition, image recognition, and gameplaying, and considerable enthusiasm in the popular press, I present tenconcerns for deep learning, and suggest that deep learning must be supplementedby other techniques if we are to reach artificial general intelligence.
2018-01-02T12:49:35Z
@machinelearning_tuts
----------
Link : http://arxiv.org/abs/1801.00631v1
arXiv.org
Deep Learning: A Critical Appraisal
Although deep learning has historical roots going back decades, neither the
term "deep learning" nor the approach was popular just over five years ago,
when the field was reignited by papers such...
term "deep learning" nor the approach was popular just over five years ago,
when the field was reignited by papers such...
NLP Overview: Modern Deep Learning Techniques Applied to Natural Language Processing
--Abstract
Trying to keep up with advancements at the overlap of neural networks and natural language processing can be troublesome. That's where the today's spotlighted resource comes in.
@machinelearning_tuts
----------
Link : https://www.kdnuggets.com/2019/01/nlp-overview-modern-deep-learning-techniques.html
--Abstract
Trying to keep up with advancements at the overlap of neural networks and natural language processing can be troublesome. That's where the today's spotlighted resource comes in.
- Jan 8, 2019.
@machinelearning_tuts
----------
Link : https://www.kdnuggets.com/2019/01/nlp-overview-modern-deep-learning-techniques.html
#course #video #ml
This series is all about neural network programming and PyTorch! We will learn how to build neural networks with PyTorch, and we’ll find that we are super close to programming neural networks from scratch, as the experience of using PyTorch is as close as it gets to the real thing! After programming neural networks with PyTorch, it’s pretty easy to see how the process works from scratch. This will lead us to a much deeper understanding of neural networks and deep learning.
@machinelearning_tuts
https://www.youtube.com/playlist?list=PLZbbT5o_s2xrfNyHZsM6ufI0iZENK9xgG
This series is all about neural network programming and PyTorch! We will learn how to build neural networks with PyTorch, and we’ll find that we are super close to programming neural networks from scratch, as the experience of using PyTorch is as close as it gets to the real thing! After programming neural networks with PyTorch, it’s pretty easy to see how the process works from scratch. This will lead us to a much deeper understanding of neural networks and deep learning.
@machinelearning_tuts
https://www.youtube.com/playlist?list=PLZbbT5o_s2xrfNyHZsM6ufI0iZENK9xgG
YouTube
PyTorch - Python Deep Learning Neural Network API
This series is all about neural network programming and PyTorch! We'll start out with the basics of PyTorch and CUDA and understand why neural networks use G...